Skip to content
View lqb464's full-sized avatar
  • University of Science - VNUHCM
  • Ho Chi Minh City
  • 20:20 (UTC +07:00)
  • Facebook lqb464

Highlights

  • Pro

Block or report lqb464

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
lqb464/README.md

🧭 At a Glance

↳ auto-updates from public repos only. Cards not loading? See note below.


I build reproducible ML pipelines — from applied AI products to production-ready model serving. Current focus: shipping AI in apps (FastAPI, Docker, full-stack) and classical ML foundations.


🧭 Career tracks

Track What I do Projects Status
📊 Data Scientist Tabular ML · clustering · imbalanced · notebooks 5 🔵 Growing
🤖 AI Engineer Agents · RAG · generative · virtual try-on · full-stack 4 🔵 Growing

9 projects across 2 tracks · full index →



🛠️ Stack

🤖 AI Engineer

PyTorch FastAPI Docker PostgreSQL

📊 Data Scientist

scikit-learn Pandas Jupyter XGBoost

Full skills breakdown — honest levels, mapped to projects



⭐ Highlights

Titanic House Prices Iris MNIST Credit Card Fraud

5 notebook-driven ML foundations — classification, regression, clustering, imbalanced data.

AgenThink RAnythinG SketClothes VirtuaLook

4 shipped apps — agents · local RAG · generative · virtual try-on.



💻 Most Used Languages

↳ public repos only



🗺️ On the roadmap

Not claiming as production skills yet:

  • CUDA · TensorRT · GPU inference optimization
  • Kubernetes · production-grade MLOps · CI/CD at scale
  • Apache Spark · Airflow · cloud data engineering
  • Cloud certifications (AWS / GCP)


📫 Connect  GitHub

© 2026 Luong Quoc Binh · Ho Chi Minh City, Vietnam


📌 Stats cards not loading?

The stats cards call the public github-readme-stats demo server, which is rate-limited. For reliable cards, render SVGs via GitHub Actions into /github-stats/ and point <img> tags at committed files. See the github-readme-stats Actions guide.

Popular repositories Loading

  1. MaskReconstructContrastive MaskReconstructContrastive Public

    Forked from HoangVo-Prog/MaskReconstructContrastive

    Python

  2. mnist-digit-recognizer mnist-digit-recognizer Public

    End-to-end MNIST digit classification: EDA, model selection (baselines + MLP), full retrain, model persistence, CLI inference, and Kaggle submission. Two-phase pipeline with documented metrics and …

    Jupyter Notebook

  3. house-prices-regression house-prices-regression Public

    Full regression lifecycle on Ames Housing: sklearn preprocessing, baseline models, Optuna tuning, stacking ensemble, and Kaggle submission. Modular Python pipeline with holdout evaluation and expor…

    Jupyter Notebook

  4. titanic-survival titanic-survival Public

    Binary survival prediction from exploration to deployment: EDA and feature engineering in notebooks, reproducible training via CLI, saved model, and Kaggle submission. Holdout accuracy ~85% with Lo…

    Jupyter Notebook

  5. iris-kmeans-clustering iris-kmeans-clustering Public

    Unsupervised learning lifecycle on Iris: scaling, elbow and silhouette analysis, K-Means training, cluster evaluation, model persistence, and CLI inference on new samples. Notebook exploration plus…

    Jupyter Notebook

  6. RNN-With-Attention-For-Machine-Translation-From-Scratch RNN-With-Attention-For-Machine-Translation-From-Scratch Public

    Forked from HoangVo-Prog/machine-translation-from-scratch

    Jupyter Notebook